Smart Adaptive Personalized Wearable Thermal Management System

This application claims the benefit of U.S. Provisional Patent Application Ser. No. 63/641,478, filed May 2, 2024, which is herein incorporated by reference in its entirety.

The human body is a heat generator and a thermally sensitive system. A large fraction of the energy input to human body as food (chemical energy) is converted to thermal energy (heat) and must be dissipated to the environment to maintain a healthy core temperature. In normal conditions, a human body's thermoregulatory system enables the heat dissipation to the environment and regulation of the core body temperature.

The thermoregulatory system's capacity to dissipate heat to the environment is dependent on ambient temperature, humidity, sunlight intensity, elevation, cardiovascular system's health, age, and several other parameters. In hot and hot-humid conditions the thermoregulatory system's capacity to dissipate heat to the environment quickly deteriorates. Over time, reduced heat dissipation to the environment (or reverse heat flow in extreme heat wave cases) may lead to thermal energy (heat) accumulation in human body and increase in core temperature above the healthy level. Elevated core temperatures lasting over an extended period (heat stress) may lead to heat stroke, permanent damage to vital organs (kidney, brain, heart, and liver), and eventually death.

The present disclosure is directed to an adaptive personalized wearable thermal management system with both cooling and heating functionality. In certain disclosed embodiments, the adaptive personalized thermal management system monitors several parameters including ambient conditions, user's biomarkers, metabolic activity level, and motion in order provide the required heat exchange capacity (needed cooling/heating power) and to maintain a comfortable and healthy thermal condition. Unlike existing technologies, the disclosed adaptive personalized thermal management system adjusts its thermal response (heating or cooling) constantly based on the data provided by its sensors, available external data, and user's own thermal profile. In certain embodiments, the accuracy of the disclosed adaptive personalized thermal management system improves over time as the system builds up a more accurate personalized profile for the wearer over a wide range of climate conditions, metabolic activity levels, and other parameters it utilizes.

To avoid heat stress and heat related illnesses, external cooling capacity can be provided to help the human body to stay in a healthy and comfortable temperature level. The current disclosure describes a wearable thermal management system, which enables a human body to maintain a healthy thermal equilibrium with the environment and keep human body temperature at a healthy and comfortable level.

Disclosed herein is a personalized adaptive thermal management system which includes a heat exchanger, a thermoelectric module in communication with the heat exchanger, a wearable interface in communication with the thermoelectric module and a user interface in communication with the thermoelectric module, wherein the user interface enables control of at least one temperature effect provided by the wearable interface. In certain embodiments, the personalized adaptive thermal management system further includes a first contact plate disposed between the thermoelectric module and the heat exchanger. The first contact plate and thermoelectric module permit heat transfer between the heat exchanger and the thermoelectric module. The system may also include a second contact plate disposed between the wearable interface and the thermoelectric module. The second contact plate and the thermoelectric module permit heat transfer between the wearable interface and the thermoelectric module.

In some embodiments, the heat exchanger is an air-cooled heat-exchanger. In some embodiments the heat exchanger is a multiphase heat exchanger. In some embodiments, the heat exchanger is a single-phase heat exchanger. In some embodiments, the heat exchanger is a phase change heat exchanger. In some embodiments, the phase change heat exchanger is a phase change material (PCM). IN some embodiments, the PCM comprises ice.

In certain embodiments, the wearable interface further comprises at least one sensor. The sensor or sensors may be configured to measure at least one of motion, temperature, acceleration, humidity, and light intensity.

The system may also further include a processor, where the processor is connected to the at least one sensor and the thermoelectric module, and where processor is configured to utilize information from the at least one sensor to control the thermoelectric module. The processor may be configured to use the information from the at least one sensor to calculate a desired voltage to be applied to the thermoelectric module.

In certain embodiments the wearable interface comprises a vest or a backpack. In some embodiments, the vest may include an integrated water dispenser, air circulation system, sensors, and customizable cooling channels for dynamic temperature regulation. In some embodiments the water dispenser system includes a reservoir or bladder for holding water, and a network of tubes or channels for distributing the water evenly throughout the vest. In some embodiments, the air circulation system includes tubes integrated into the vest and connected to an air pump, and further comprising a plurality of openings disposed throughout the vest and configured to allow air flow to evaporate water from a wet vest.

In certain embodiments the processor is configured to utilize sensor data to monitor a user's physiological parameters and at least one environmental data measurement to dynamically adjust a system cooling mode. In some embodiments the sensors monitor a user's body temperature, ambient temperature and humidity, and adjust at least one of a water flow and air flow based on the monitoring. In some embodiments, the system contains an alarm system to alert a user or a caregiver for the user of the system.

Reference will now be made in detail to various embodiments of the disclosed subject matter, one or more examples of which are set forth below. Each embodiment is provided by way of explanation of the subject matter, not limitation thereof. In fact, it will be apparent to those skilled in the art that various modifications and variations may be made in the present disclosure without departing from the scope or spirit of the subject matter. For instance, features illustrated or described as part of one embodiment, may be used in another embodiment to yield a still further embodiment.

In general, the present disclosure is directed to a cooling vest designed to offer superior temperature regulation in diverse environments and activities. Certain embodiments are provided below which describe various functional pieces of the adaptive personal thermal management system. Control of the various components of the system may be informed by computing systems such as those contained in.

This patent application discloses a personalized adaptive thermal management system. The disclosed system is smart, lightweight, quiet, compact, and easy to use. In certain embodiments, the system is enhanced with AI operation features which control or inform the control mechanisms of the system. The system determines the required/needed cooling/heating power based on an array of inputs from the user and the environment and delivers the optimum cooling/heating power. These inputs may include but are not limited to the user's metabolic activity level, heartrate, weight, height, body temperature, breathing rate, and other biomarkers in addition to ambient temperature, humidity, sunlight intensity and other parameters. In certain embodiments, the system generates a personalized and dynamic response to each user based on the user's thermal profile. The minuscule thermal mass, rapid response, and compact and efficient design of the system enables it to follow the input array closely and generate the personalized thermal response tuned to maintain the wearer in a thermally comfortable zone and prevent heat stress, heat stroke, and other heat/cold related illnesses.

Turning now to a detailed discussion of the figures,present block diagrams of an exemplary control system for managing a user's thermal state. These control systems may utilize advanced modeling techniques featuring AI-enhanced control, or may utilize conventional means of modeling or control.

depicts a block diagram of an example computing systemthat performs training of a machine learning modelaccording to example embodiments of the present disclosure. The systemincludes a user computing device, a server computing system, and a training computing systemthat are communicatively coupled over a network.

The user computing deviceincludes one or more processorsand a memory. The one or more processorscan be any suitable processing device (e.g., a processor core, a microprocessor, an ASIC, an FPGA, a controller, a microcontroller, etc.) and can be one processor or a plurality of processors that are operatively connected. The memorycan include one or more non-transitory computer-readable storage media, such as RAM, ROM, EEPROM, EPROM, flash memory devices, magnetic disks, etc., and combinations thereof. The memorycan store dataand instructionswhich are executed by the processorto cause the user computing deviceto perform operations.

In some implementations, the user computing devicecan store or include one or more machine learning models. For example, the machine learned modelscan be or can otherwise include various machine-learned models such as neural networks (e.g., deep neural networks) or other types of machine-learned models, including non-linear models and/or linear models. Neural networks can include feed-forward neural networks, recurrent neural networks (e.g., long short-term memory recurrent neural networks), convolutional neural networks or other forms of neural networks. Some example machine-learned models can leverage an attention mechanism such as self-attention. For example, some example machine-learned models can include multi-headed self-attention models (e.g., transformer models).

In some implementations, the one or more machine learning modelscan be received from the server computing systemover network, stored in the user computing device memory, and then used or otherwise implemented by the one or more processors.

More particularly, the machine learned modelmay be used to aggregate and categorize data relating to temperature, humidity, heart rate, blood oxygen level, humidity, or any following described parameters.

Additionally or alternatively, one or more machine learning modelscan be included in or otherwise stored and implemented by the server computing systemthat communicates with the user computing deviceaccording to a client-server relationship. For example, the machine learning modelscan be implemented by the server computing systemas a portion of a web service Thus, one or more modelscan be stored and implemented at the user computing deviceand/or one or more modelscan be stored and implemented at the server computing system.

The user computing devicecan also include one or more user input componentsthat receives user input. For example, the user input componentcan be a touch-sensitive component (e.g., a touch-sensitive display screen or a touch pad) that is sensitive to the touch of a user input object (e.g., a finger or a stylus). The touch-sensitive component can serve to implement a virtual keyboard. Other example user input components include a microphone, a traditional keyboard, or other means by which a user can provide user input.

The server computing systemincludes one or more processorsand a memory. The one or more processorscan be any suitable processing device (e.g., a processor core, a microprocessor, an ASIC, an FPGA, a controller, a microcontroller, etc.) and can be one processor or a plurality of processors that are operatively connected. The memorycan include one or more non-transitory computer-readable storage media, such as RAM, ROM, EEPROM, EPROM, flash memory devices, magnetic disks, etc., and combinations thereof. The memorycan store dataand instructionswhich are executed by the processorto cause the server computing systemto perform operations.

In some implementations, the server computing systemincludes or is otherwise implemented by one or more server computing devices. In instances in which the server computing systemincludes plural server computing devices, such server computing devices can operate according to sequential computing architectures, parallel computing architectures, or some combination thereof.

As described above, the server computing systemcan store or otherwise include one or more machine learning models. For example, the modelscan be or can otherwise include various machine-learned models. Example machine-learned models include neural networks or other multi-layer non-linear models. Example neural networks include feed forward neural networks, deep neural networks, recurrent neural networks, and convolutional neural networks. Some example machine-learned models can leverage an attention mechanism such as self-attention. For example, some example machine-learned models can include multi-headed self-attention models (e.g., transformer models).

The user computing deviceand/or the server computing systemcan train the modelsand/orvia interaction with the training computing systemthat is communicatively coupled over the network. The training computing systemcan be separate from the server computing systemor can be a portion of the server computing system.

The training computing systemincludes one or more processorsand a memory. The one or more processorscan be any suitable processing device (e.g., a processor core, a microprocessor, an ASIC, an FPGA, a controller, a microcontroller, etc.) and can be one processor or a plurality of processors that are operatively connected. The memorycan include one or more non-transitory computer-readable storage media, such as RAM, ROM, EEPROM, EPROM, flash memory devices, magnetic disks, etc., and combinations thereof. The memorycan store dataand instructionswhich are executed by the processorto cause the training computing systemto perform operations. In some implementations, the training computing systemincludes or is otherwise implemented by one or more server computing devices.

The training computing systemcan include a model trainerthat trains the machine-learned modelsand/orstored at the user computing deviceand/or the server computing systemusing various training or learning techniques, such as, for example, backwards propagation of errors. For example, a loss function can be backpropagated through the model(s) to update one or more parameters of the model(s) (e.g., based on a gradient of the loss function). Various loss functions can be used such as mean squared error, likelihood loss, cross entropy loss, hinge loss, and/or various other loss functions. Gradient descent techniques can be used to iteratively update the parameters over a number of training iterations.

In some implementations, performing backwards propagation of errors can include performing truncated backpropagation through time. The model trainercan perform a number of generalization techniques (e.g., weight decays, dropouts, etc.) to improve the generalization capability of the models being trained.

In particular, the model trainercan train the machine learning modelsand/orbased on a set of training data. The training datacan include, for example, past physiological information, past ambient information, or any of the following described parameters.

In some implementations, if the user has provided consent, the training examples can be provided by the user computing device. Thus, in such implementations, the modelprovided to the user computing devicecan be trained by the training computing systemon user-specific data received from the user computing device. In some instances, this process can be referred to as personalizing the model.

The model trainerincludes computer logic utilized to provide desired functionality. The model trainercan be implemented in hardware, firmware, and/or software controlling a general purpose processor. For example, in some implementations, the model trainerincludes program files stored on a storage device, loaded into a memory and executed by one or more processors. In other implementations, the model trainerincludes one or more sets of computer-executable instructions that are stored in a tangible computer-readable storage medium such as RAM, hard disk, or optical or magnetic media.

The networkcan be any type of communications network, such as a local area network (e.g., intranet), wide area network (e.g., Internet), or some combination thereof and can include any number of wired or wireless links. In general, communication over the networkcan be carried via any type of wired and/or wireless connection, using a wide variety of communication protocols (e.g., TCP/IP, HTTP, SMTP, FTP), encodings or formats (e.g., HTML, XML), and/or protection schemes (e.g., VPN, secure HTTP, SSL).

depicts a set of exemplary modes operating on a computing device. As depicted, cooling mode, heating mode, or other user customized modesmay receive various inputs in the operation of these modes. For example, sensorsmay provide sensor data, context managermay provide context data, device state variablesmay provide device state data, and other additional componentsmay provide additional data (e.g., statistical data).

In some implementations, the input to the machine-learned model(s) of the present disclosure can be statistical data. Statistical data can be, represent, or otherwise include data computed and/or calculated from some other data source. The machine-learned model(s) can process the statistical data to generate an output. As an example, the machine-learned model(s) can process the statistical data to generate a recognition output. As another example, the machine-learned model(s) can process the statistical data to generate a prediction output. As another example, the machine-learned model(s) can process the statistical data to generate a classification output. As another example, the machine-learned model(s) can process the statistical data to generate a segmentation output. As another example, the machine-learned model(s) can process the statistical data to generate a visualization output. As another example, the machine-learned model(s) can process the statistical data to generate a diagnostic output.

In some implementations, the input to the machine-learned model(s) of the present disclosure can be sensor data. The machine-learned model(s) can process the sensor data to generate an output. As an example, the machine-learned model(s) can process the sensor data to generate a recognition output. As another example, the machine-learned model(s) can process the sensor data to generate a prediction output. As another example, the machine-learned model(s) can process the sensor data to generate a classification output. As another example, the machine-learned model(s) can process the sensor data to generate a segmentation output. As another example, the machine-learned model(s) can process the sensor data to generate a visualization output. As another example, the machine-learned model(s) can process the sensor data to generate a diagnostic output. As another example, the machine-learned model(s) can process the sensor data to generate a detection output.

illustrates a high-level block diagram of one embodiment adaptive personalized thermal management system. Useris equipped with wearable thermal interface unitwhich provides heating and cooling to user. In the disclosed embodiment, Useris also able to interact with user interface unit. However, in certain embodiments user interface unitmay not be present, or may be an extremely simplified interface. Throughout, thermal exchange occurs at exchanges.

User interface unitis configured to interact with and inform power and control unit. Power and control unitis operatively connected to heat exchange components: wearable thermal interface unit (WITU), active thermal unit (ATU), and heat exchange unit (HEU). Power and control unit provides and adjusts power to each of these units. In certain embodiments, sensors and electronics are housed in a water-resistant, durable casing. The power and control unit and associated sensors and electronics may be of a compact, lightweight design for seamless integration into the wearable thermal interface unit.

Wearable thermal interface unit (WITU)interfaces with userand may be in the form of a vest, hat, helmet, neck collar, shirt, pants, shorts, or other wearable item, such as a backpack or a portion of a backpack. Further, wearable thermal interface unitmay be a combination of these wearable items, e.g., a vest and a hat, vest hat and collar, etc. The wearable item(s) of wearable thermal interface unitincludes a fluid circulation system with tubing, contact surfaces, and materials that facilitate heat transfer from the skin surface to the circulating fluid, or vice-versa.

Active thermal unit (ATU)is itself operatively connected to wearable thermal interface unitand may exchange heating and cooling with wearable thermal interface. Active thermal unitadjusts the temperature of the working fluid which flows into the wearable thermal interface unit. Active thermal unitmay employ a single or a combination of cooling-heating mechanisms to change the temperature of the working fluid circulating through the wearable thermal interface unit and active-thermal unit. For example, in certain embodiments, ATUmay utilize thermoelectric modules (TECs) coupled with an air heat exchanger. In another embodiment, ATUmay utilizes TECs coupled with a liquid heat-exchanger. In another embodiment, ATUmay utilize TECs coupled with a phase-change-heat-exchanger, such as solid-liquid, liquid-vapor, solid-vapor, or a combination of all three. In other embodiments, a combination of TECs coupled with different heat-exchangers may be utilized, e.g., both an air and liquid heat-exchanger, an air and phase-change heat-exchanger, a liquid and phase-change heat exchanger, or a combination of all three. In each instance, TEC operation may be optimized based on the teachings contained in this disclosure.

Furthermore, active thermal unitmay exchange heating and cooling with heat exchange unit. Heat exchange unitis configure to interface and provide exchange of hot/cold with the outside environment (or relevant ambient environment). When adaptive personalized thermal management systemis operating in a cooling mode, heat exchange unitoperates as a heat dissipation mechanism, absorbing the total energy from userand waste heat generated by ATU.

User interface unitallows control of adaptive personalized thermal management system. In certain embodiments, the user interface associated with the user interface unit is provided using an app on a user's phone, smart watch, or other similar device. In other embodiments, the user interface may be provided by attachment to the wearable systems, with either a wired or wireless connection to power and control unit. In other embodiments, a combination of an app-based interface and a directly connected interface may be used. User interface unitallows the user to control various settings and functions of adaptive personalized thermal management system, including, for example, setting the desired temperature, choosing from existing present programs, or activating a personalized adaptive mode, which may incorporated various AI-based methods or may otherwise use adaptive logic based on the input of various items of the input array.

In operation, the adaptive personalized thermal management system is configured to operate utilizing an array of input data which informs power and control unit. Input data may include both user-specific data and environment specific data. For example, user-specific data may include, but is not limited to, a user's temperature, motion, heart rate, bloody oxygen level, breathing rate, and metabolic activity level. Environment-specific data may include, but is not limited to temperature, humidity, sunlight intensity, elevation, and windspeed. These data may be considered as point-in-time measurements, historical data, or use predictive information, for example.

Adaptive personalized thermal management systemvia power and control unitmay be operated in a manual mode through user input via the user interface. Systemmay also be operated using adaptive operation which leverages an integrated AI system such as the one disclosed in connection with. In other modes of operation, adaptive personalized thermal management system may utilize previously programmed operations. For example, a user undergoing medical treatments where cooling or heating may be valuable for the health or comfort of a patient, a programmed response may be utilized. Similarly, if certain emergency response situations (e.g., heat stroke, overheating, or known intense thermal environments) are encountered, a programmed treatment may be utilized. Additionally, a combination of any of the above modes may be utilized.

An operating mode for adaptive personalized thermal management system may be considered a Thermal Operating Mode comprising a cooling mode and a heating mode. In a cooling mode, circulating fluid is cooled to the desired temperature by Active Thermal Unit. The cooled fluid will then enter a fluid distribution system embedded in the structure of the wearable item (e.g., vest, hat, neck collar, etc.) and is brought into thermal contact with the user's skin (either directly or indirectly across clothing) where it provides the required cooling power to maintain user's temperature at a healthy level. As a result of heat exchange with the user's body the fluid temperature increases. The warm fluid then flows back to the wearable system heat-exchange unit to be cooled again and repeat the cycle again.

In a heating mode, an operation similar to the cooling mode occurs, but essentially in reverse. Circulating fluid is warmed up in Active Thermal Unitto a temperature higher than the user's body temperature. The circulating fluid then enters the wearable fluid distributing system and warms the skin. The cooled fluid then flows back to Active Thermal Unitto repeat the cycle.

Certain non-limiting examples of possible use cases for the wearable the following examples are given in more detail below.

In one example, the personalized adaptive thermal management system may be deployed in workplace environments. For example, the personalized adaptive thermal management system may protect workers exposed to heat from heat stress and prevents decline in workplace productivity. Through its use, the system helps workers to stay thermally comfortable and prevents dehydration. Due to its continuous monitoring of user vital data, the personalized adaptive thermal management system can alert the user to stop working when heat stress/stroke is imminent.

Multiple different medical applications may employ the personalized adaptive thermal management system, including in diagnostic, safety and prevention, and emergency response settings. Furthermore, the personalized adaptive thermal management system may be used in connection with other medical treatments which may cause heating or cooling sensation to the user, e.g., chemotherapy treatments. Some exemplary aspects of the diagnostic, safety and prevention, and emergency response uses are detailed below:

The ability of the human body to regulate its temperature and withstand extreme heat or cold is often closely linked to the health of its cardiovascular and other essential systems. By utilizing the array of inputs available to the personalized adaptive thermal management system the system may build a dynamic personal thermal profile for each user over time. An artificial intelligence system may utilize the thermal profile in addition to monitored parameters to provide the thermal response. The thermal profile for each user and his/her health data monitored by multiple sensors can be utilized for a wide range of medical diagnosis purposes.